{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XW7BOJHQDSTR46BSV6SNKN5FAW","short_pith_number":"pith:XW7BOJHQ","schema_version":"1.0","canonical_sha256":"bdbe1724f01ca71e7832afa4d537a505b579e65c08cd7f1ac7ffa526ff6aa605","source":{"kind":"arxiv","id":"2602.11933","version":2},"attestation_state":"computed","paper":{"title":"Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abderrahmane Issam, Gerasimos Spanakis, Jan Scholtes, Yusuf Can Semerci","submitted_at":"2026-02-12T13:30:12Z","abstract_excerpt":"End-to-End Speech Translation (E2E-ST) has seen significant advancements, yet current models are primarily benchmarked on curated, \"clean\" datasets. This overlooks critical real-world challenges, such as morphological robustness to inflectional variations common in non-native or dialectal speech. In this work, we adapt a text-based adversarial attack targeting inflectional morphology to the speech domain and demonstrate that state-of-the-art E2E-ST models are highly vulnerable it. While adversarial training effectively mitigates such risks in text-based tasks, generating high-quality adversari"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.11933","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-12T13:30:12Z","cross_cats_sorted":[],"title_canon_sha256":"ffad25501dfea44479bc9f1bfc356ce86d6b7c0670f5c9486ddbd31cd5269d2b","abstract_canon_sha256":"86dcbd4a41a01b729f1c41cffe37f4f21b46272292905653ae9ad1a4e5ab39e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:50.343176Z","signature_b64":"rTy/xgBrJhh5c5J/KcMV08Uljl8jBQCiGJBk5zTZcOg48HTWDfg0tojQ9D5X4u2OVcxGrEZbuKNmgEnDUprUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdbe1724f01ca71e7832afa4d537a505b579e65c08cd7f1ac7ffa526ff6aa605","last_reissued_at":"2026-06-25T01:17:50.342769Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:50.342769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abderrahmane Issam, Gerasimos Spanakis, Jan Scholtes, Yusuf Can Semerci","submitted_at":"2026-02-12T13:30:12Z","abstract_excerpt":"End-to-End Speech Translation (E2E-ST) has seen significant advancements, yet current models are primarily benchmarked on curated, \"clean\" datasets. This overlooks critical real-world challenges, such as morphological robustness to inflectional variations common in non-native or dialectal speech. In this work, we adapt a text-based adversarial attack targeting inflectional morphology to the speech domain and demonstrate that state-of-the-art E2E-ST models are highly vulnerable it. While adversarial training effectively mitigates such risks in text-based tasks, generating high-quality adversari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11933","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.11933/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.11933","created_at":"2026-06-25T01:17:50.342827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11933v2","created_at":"2026-06-25T01:17:50.342827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11933","created_at":"2026-06-25T01:17:50.342827+00:00"},{"alias_kind":"pith_short_12","alias_value":"XW7BOJHQDSTR","created_at":"2026-06-25T01:17:50.342827+00:00"},{"alias_kind":"pith_short_16","alias_value":"XW7BOJHQDSTR46BS","created_at":"2026-06-25T01:17:50.342827+00:00"},{"alias_kind":"pith_short_8","alias_value":"XW7BOJHQ","created_at":"2026-06-25T01:17:50.342827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW","json":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW.json","graph_json":"https://pith.science/api/pith-number/XW7BOJHQDSTR46BSV6SNKN5FAW/graph.json","events_json":"https://pith.science/api/pith-number/XW7BOJHQDSTR46BSV6SNKN5FAW/events.json","paper":"https://pith.science/paper/XW7BOJHQ"},"agent_actions":{"view_html":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW","download_json":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW.json","view_paper":"https://pith.science/paper/XW7BOJHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11933&json=true","fetch_graph":"https://pith.science/api/pith-number/XW7BOJHQDSTR46BSV6SNKN5FAW/graph.json","fetch_events":"https://pith.science/api/pith-number/XW7BOJHQDSTR46BSV6SNKN5FAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW/action/storage_attestation","attest_author":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW/action/author_attestation","sign_citation":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW/action/citation_signature","submit_replication":"https://pith.science/pith/XW7BOJHQDSTR46BSV6SNKN5FAW/action/replication_record"}},"created_at":"2026-06-25T01:17:50.342827+00:00","updated_at":"2026-06-25T01:17:50.342827+00:00"}